In order to gain better insight into the preferences and behaviors of drivers when they interact with Advanced Driving Assistance Systems (ADAS), Subaru would like to collect naturalistic data from drivers. Students on the Subaru team will design and execute a complete data collection system in a test vehicle provided by Subaru that acquires and stores data including video, vehicle accelerometer, and location data for analysis at a later date.
Abstract:
As the automotive market for Advanced Driving Assistance Systems (ADAS) continues to grow, Subaru wants to evaluate how consumers interact with these systems. To ensure continued growth in sales, Subaru must understand the North American customer’s needs. However, various challenges immediately present themselves upon attempting to understand the customer, not the least of which is that customers often do not know what they really want. Naturalistic driving data collection involves monitoring and collecting data on drivers displaying natural behavior in the course of regular driving. North America is Subaru’s most valuable market. Thus, Subaru seeks to understand the driving behavior of North American customers by collecting naturalistic driving data, and subsequently analyzing them to reveal true customer expectations. Students on the Subaru team will design and execute a complete data collection system in a test vehicle provided by Subaru that acquires and stores video, vehicle accelerometer, and location data for analysis at a later date.
Impact:
The ability to perform naturalistic driving studies on ADAS systems will provide Subaru insights into consumer behavior that will lead to more effective and desirable systems. This will improve driver safety, customer satisfaction, and Subaru’s position in the automotive market.
Full Project Details
Electronic Sensor Systems Development (2–3 students)
Specific Skills: Sensor selection and integration. Prior or concurrent coursework and/or practical experience EECS 215: Introduction to Electrical Circuits/EECS 314: Electrical Circuits, Systems, and Applications or Applied electrical circuits and systems
Likely Majors: CE, EE, MECHENG, ROB
Database Design/Dynamic Data Acquisition (1-2 students)
Specific Skills: Database Design, I/O Data systems (WIFI). EECS 484 preferred. Please highlight in your personal statement
Likely Majors: CS, CE, EE
Web GUI Tool Development (1-2 students)
Specific Skills: Web-based GUI design, Video processing. Must have completed EECS 281
Likely Majors: CS (or relevant experience)
Mechanical Design with Sensor integration (1-2 students)
Specific Skills: Incorporation of a wide range of sensors into a greater system. Basic Knowledge of embedded systems, signal processing, etc. Priority given to students who have completed EE 315 (or equivalent) and/or have sensor integration experience.
Likely Majors: MECHENG, ISD-AUTO, ISD-GAME
Sponsor Mentors
John Hoo
Engineer – ADAS & Vehicle Performance Engineering
John has been working for Subaru since 2017. He has his BSc in Materials Science & Engineering from Purdue University. His primary focus area is Electronic Platform Design. John received further training from Subaru in the USA and Japan, where he developed cross-language and cultural communication skills. To ensure the success of collaborative research efforts, he recently relocated to Michigan.
Executive Mentor
Daisuke Mashiyama
Manager – ADAS & Vehicle Performance Engineering
Daisuke has been with Subaru since 2015, and has been engaged in the
field of ADAS ever since. He has his MSc in Electrical Engineering from
Yokohama National University, and is currently looking for advanced technology to contribute towards Subaru’s goal of eliminating traffic fatalities. He enjoys tennis and video games.
Faculty Mentor
Baris Kasikci
Baris Kasikci an assistant professor in the Electrical Engineering and Computer Science Department at the University of Michigan. His research is centered around developing techniques, tools, and environments that help developers build more reliable, secure, and efficient software. He is interested in developing techniques and building systems that allow programmers to better reason about their code. He is also interested in system support for emerging hardware platforms, efficient runtime instrumentation, hardware and runtime support for enhancing system security, and program analysis.
Baris Kasikci is the recipient of an NSF CAREER award, a Microsoft Research Faculty Fellowship, an Intel Rising Star Award, a VMware Early Career Faculty Grant, a Google Faculty Award, and multiple Google and Intel Awards. He received the 2016 Roger Needham PhD Award for the best PhD thesis in computer systems in Europe and the 2016 Patrick Denantes Memorial Prize for best PhD thesis in the Department of Information and Communication Sciences at EPFL. Previously, he was a researcher in the Systems and Networking Group at Microsoft Research Cambridge. He also held roles at Intel, VMware and Siemens.
Course Substitutions: Honors, ChE Elective, CS MDE/Capstone, CE MDE, EE MDE, IOE Grad Cognate, ISD AUTO 503, ISD GAME, MECHENG 490, ROB 590, SI Elective, SI Grad Cognate
Citizenship Requirements: This project is open to all students on campus.
IP/NDA: Students will sign IP/NDA document(s) that are unique to Subaru R&D.
In Person/Remote Participation Options: Students on this team must be able to be physically present on campus in Ann Arbor and able and willing to travel to Subaru R&D in the Ann Arbor area to work on physical prototypes as local safety protocols allow.
Internship/Summer Project Activities: Students who have the legal right to work in the US will be guaranteed an interview for a 2022 internship. The interviews will take place by the end January of 2022. The internship program may not be confined to the project’s subject matter.